Abstract: An arithmetic coding scheme is provided for coding and decoding 3D data and improves coding efficiency for mesh displacements and high-quality coding, and decoding of the 3D data. A 3D data decoding apparatus is also provided for decoding coded data. The apparatus contains an arithmetic decoder that is configured to arithmetically decode a mesh displacement from the coded data. The arithmetic decoder decodes, from the coded data, a first flag indicating whether a coefficient of the mesh displacement has an absolute value greater than 0, a second flag indicating whether the coefficient has an absolute value greater than 1, and a third flag indicating whether the coefficient has an absolute value greater than 2.

Abstract: A video decoding apparatus is a video decoding apparatus for deriving a prediction image by using a reference picture included in a reference picture list.

Abstract: Provided is a video decoding apparatus for decoding coded data of a tile group in which a picture is split into rectangular regions, the tile group being composed of segments, the video decoding apparatus including: a header decoder configured to decode the number of tiles, a WPP enabled flag, and a slice enabled flag indicating whether segments in a target tile group are rectangular tiles, CTU rows, or slices from a tile group header, wherein the header decoder is configured to decode only one of the number of tiles being two or more, the WPP enabled flag being 1, and the slice enabled flag being 1 in one tile group.

Abstract: A video coding scheme for encoding and decoding 3D data encodes and decodes a mesh displacement image as an image in a 4:2:0 format, reduces distortion caused by encoding, and encodes and decodes 3D data with high quality. A 3D data decoding apparatus includes a video decoder that is configured to decode a mesh displacement image decoded from a geometry video stream in which a Unit Type of coded data is V3C_GVD and a displacement unmapper that is configured to derive a mesh displacement per position pos and component compIdx from the mesh displacement image. The displacement unmapper is further configured to derive a Y coordinate of a geometry image from a product of a height and a variable from 0 to a value indicating a number of dimensions of geometry minus 1 to derive the mesh displacement in a case that the geometry image is in a 4:2:0 format.

Abstract: In a case that all network parameters are adaptively switched, it is difficult to switch the parameters for each small block, such as a CTU. There is a problem in that, in a case that ALF class classification and filtering are successively performed in ALF parallel after application of an NN filter, processing requires time. By selecting an NN model in a slice header and selecting a network layer finetuned in a CTU, the NN model can be adaptively selected even for each small block. By performing ALF class classification in an image before being subjected to an NN filter and performing ALF processing using an image subjected to NN filtering processing and ALF class information, the NN filtering processing and the ALF class classification can be performed in parallel.

Abstract: A video decoding apparatus including a parameter decoding circuit, a prediction parameter derivation circuit, a motion compensation circuit, and a weighted prediction circuit is provided. The parameter decoding circuit is configured to decode a flag and a syntax element. The prediction parameter derivation circuit is configured to derive inter prediction parameters. The motion compensation circuit is configured to generate interpolation images based on the inter prediction parameters and reference pictures. The weighted prediction circuit is configured to derive the weight coefficients using the syntax element, and generate a prediction image using the interpolation images and the weight coefficients. When the flag indicates that the weighted prediction information is present in the slice header, the weighted prediction circuit sets a variable NumWeightL1 indicating a number of weights for a reference picture list 1 to be equal to a value of a variable NumRefIdxActive[1] derived from the slice header.

Abstract: Object There is the problem in the related art that the relationship between a patch size which is a unit of processing of a neural network and the sizes of input and output pictures is not clearly defined.

Abstract: A 3D data decoding apparatus for decoding coded data and decoding 3D data including attribute information includes a header decoder that decodes characteristics information of refinement and activation information of the refinement, and a refiner that performs refinement processing of an attribute frame or an geometry frame. Refinement target information indicating which of an occupancy, a geometry, or an attribute is to be used is decoded from coded data of the characteristics information and the refinement is performed using an image specified according to the refinement target information.

Abstract: An image decoding apparatus capable of more preferably applying inverse non-separable transform and techniques related thereto are provided. A video decoding apparatus includes a header decoder configured to decode a flag indicating a high accuracy coding mode from a sequence parameter set SPS, a scaling processing unit configured to perform inverse quantization on a transform coefficient for each transform block, and an inverse transform processing unit configured to perform inverse transform. The scaling processing unit switches whether a variable for indicating a range of the transform coefficient depends on a bit depth or does not depend on the bit depth, based on the flag and a size of the transform block.

Abstract: According to an aspect of the present disclosure, an image decoding apparatus for decoding information specifying a neural network includes: header decoding circuitry that decodes an input tensor identification parameter specifying a process for deriving an input tensor input for a post filter of the neural network. The input tensor identification parameter is a parameter related to a color component channel.

Abstract: In a case that a scaling value of neural network filter strength is set equal to 0, a decoded image before a deblocking filter is output, and thus block noise occurs. In a case that luma and chroma parameters are not taken into consideration, processing for an image of multiple transfer functions and chroma parameters is not appropriately performed. In a unit of a prescribed block, by using a parameter indicating a degree of application of the NN filter, an image after the deblocking filter and an image after an NN filter are combined using a different ratio of the images. Filter processing of a luma image is switched based on a luma parameter, and filter processing of a chroma image is switched based on a chroma parameter.

Abstract: A video decoding apparatus includes a matrix reference pixel derivation unit that derives, as a reference image, an image obtained by downsampling an image adjacent to a top side and a left side of a target block, a mode derivation unit that derives a candidate list of prediction modes used for a target block according to the reference image and a size of the target block, a prediction processing parameter derivation unit that derives a prediction processing parameter used to derive a prediction image according to the candidate list, a matrix intra prediction mode indicator, and the size of the target block, a matrix prediction image derivation unit that derives a prediction image based on an element of the reference image and the prediction processing parameter, and a matrix prediction image interpolation unit that derives the prediction image or an image obtained by interpolating the prediction image, as a prediction image.

Abstract: A device may comprise one or more processors configured to: derive variables BitDepth Y and BitDepthC equal to BitDepth Y and BitDepthC; decode a slice QP SliceQPY and a offset QpBdOffsetY; derive StrengthControlVal equal to a value of (SliceQpY+QpBdOffsetY)÷(51+QpBdOffsetY) of a first slice of current coded picture; and set StrengthControlVal to an input tensor.

Abstract: A video decoding apparatus includes matrix reference pixel derivation circuitry that derives reference samples by using top neighboring samples and left neighboring samples of a current block, weight matrix derivation circuitry that derives a weight matrix, matrix prediction image derivation circuitry that derives a prediction image, and matrix prediction image interpolation circuitry that derives a predicted image by using the prediction image. A size index is derived according to a value of a target block width and a value of a target block height. A prediction size is derived using the size index. In a case that a first condition, that both the value of the transform block width and the value of the transform block height are equal to 4, is true, the size index is set equal to 0 and the prediction size is set equal to 4.

Abstract: A video decoding apparatus is a video decoding apparatus for deriving a prediction image by using a reference picture included in a reference picture list.

Abstract: A device is provided with: a first transformer which transforms an coding unit (CU); and a second transformer which transforms a part of first transform coefficients output from the first transformer, wherein the second transformer transforms at least any of the first transform coefficients for a region (first region) having different sizes in a horizontal direction and a vertical direction or the first transform coefficients for a non-rectangular region (second region).

Abstract: An image decoding apparatus and an image coding apparatus that reduce complexity of high image quality processing are implemented. The image decoding apparatus includes an inter prediction parameter decoding processing unit that includes processing of, regarding two motion vectors, modifying the two motion vectors from an error of two prediction images. In a case that neither of the two prediction images is a case of weighted prediction, the processing of modifying the two motion vectors is performed.

Abstract: Object There is a problem that, in specifications, although 0 can be defined as the number of weights in weighted prediction, operation cannot be performed in a case that the number of weights is 0. Solution to Problem The number of weights of a reference list from coded data is decoded. The number of the weights of the reference list is set equal to or more than 1. A flag indicating whether a weight coefficient and an offset value are present is decoded for each index of the reference list, according to the number of the weights. The weight coefficient and the offset value are decoded in a case that a value of the flag is true. An interpolation image of a reference picture is multiplied by the weight coefficient, the offset value is added, and a prediction image is generated.

Abstract: In a case that two reference picture lists are selected with one index value, the reference picture lists may not be determinable depending on the number of two reference picture list structures. Provided is a prediction unit that decodes a reference picture list structure including multiple reference picture lists and selects two reference picture lists from the reference picture list structure for each picture or for each slice. The prediction unit selects two reference picture lists with one index value depending on the number of two reference picture list structures.

Abstract: An image decoding apparatus is implemented that can suppress a decrease in coding efficiency in a case that a high compression rate is achieved. The image decoding apparatus includes a parameter decoder, and the parameter decoder decodes a skip flag indicating whether a skip mode is applied, and in a case that the skip flag does not indicate the skip mode, decodes a merge flag indicating whether a merge mode is applied, and in a case that the merge flag does not indicate the merge mode, decodes an MMVD flag indicating whether an MMVD mode is applied.